mailitics

Tag: beta

  • Mutual Information Collapse Explains Disentanglement Failure in $beta$-VAEs

    Mutual Information Collapse Explains Disentanglement Failure in $beta$-VAEs arXiv:2602.09277v1 Announce Type: new Abstract: The $beta$-VAE is a foundational framework for unsupervised disentanglement, using $beta$ to regulate the trade-off between latent factorization and reconstruction fidelity. Empirically, however, disentanglement performance exhibits a pervasive non-monotonic trend: benchmarks such as MIG and SAP typically peak at intermediate $beta$ and…

  • Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation

    Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation arXiv:2601.22367v1 Announce Type: new Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature $beta>0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset…

  • Scaled Beta Models and Feature Dilution for Dynamic Ticket Pricing

    Scaled Beta Models and Feature Dilution for Dynamic Ticket Pricing arXiv:2507.23767v1 Announce Type: new Abstract: A novel approach is presented for identifying distinct signatures of performing acts in the secondary ticket resale market by analyzing dynamic pricing distributions. Using a newly curated, time series dataset from the SeatGeek API, we model ticket pricing distributions as…

  • A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data

    A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data arXiv:2412.09779v1 Announce Type: new Abstract: Recent advances have revealed that the rate of convergence of the expected test error in deep supervised learning decays as a function of the intrinsic dimension and not the dimension $d$ of the input space. Existing…

  • An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits

    An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits arXiv:2412.02861v1 Announce Type: new Abstract: We study the performance of the Thompson Sampling algorithm for logistic bandit problems, where the agent receives binary rewards with probabilities determined by a logistic function $exp(beta langle a, theta rangle)/(1+exp(beta langle a, theta rangle))$. We focus on the setting where…